Ablation results on the 17,858 gene set.

Although individual Mendelian diseases—those caused by a single gene—are rare, their collective disease burden is substantial. Identifying the causal gene for each condition is essential for accurate diagnosis and effective treatment. Yet, despite decades of research, the genetic basis of more than half of all known Mendelian diseases remains unresolved. To address this gap, we introduce MENDELSEEK, a machine learning framework that predicts Mendelian genes by integrating residue variation scores with pathway participation, Gene Ontology processes, and protein language model features. In benchmarking across 16,946 human genes with 10-fold cross-validation, MENDELSEEK achieved an AUC of 0.869 and an AUPR of 0.737—substantially outperforming the next best methods, ENTPRISE+ENTPRISE-X (AUC 0.781; AUPR 0.626), and REVEL (AUC 0.585; AUPR 0.401). When applied to the full set of 17,858 human genes, MENDELSEEK predicted 1,277 novel Mendelian gene candidates with precision greater than 0.7. Analysis further revealed that Mendelian genes engage in significantly more protein-protein interactions than non-Mendelian genes and are evolutionarily ancient. Together, these results highlight MENDELSEEK as a major advance over existing methods, offering new insights into the biochemical features that distinguish Mendelian from non-Mendelian genes.尽管单基因致病的孟德尔遗传病（Mendelian diseases）单病种较为罕见，但其整体疾病负担却相当可观。精准鉴定每种疾病的致病基因，是实现准确诊断与有效治疗的核心前提。然而，尽管历经数十年研究，目前仍有超过半数已知的孟德尔遗传病的遗传基础尚未阐明。为填补这一研究空白，我们提出了MENDELSEEK——一款通过整合残基变异评分、通路参与信息、基因本体（Gene Ontology）过程特征与蛋白质语言模型（protein language model）特征，预测孟德尔遗传病致病基因的机器学习框架。在包含16946个人类基因的数据集上开展10折交叉验证的基准测试中，MENDELSEEK取得了0.869的受试者工作特征曲线下面积（AUC）与0.737的精确召回曲线下面积（AUPR），性能显著优于当前表现第二的ENTPRISE+ENTPRISE-X（AUC 0.781；AUPR 0.626）与REVEL（AUC 0.585；AUPR 0.401）。当将MENDELSEEK应用于全部17858个人类基因集时，其精准预测出1277个精度大于0.7的全新孟德尔基因候选者。进一步分析显示，孟德尔遗传病致病基因相较于非孟德尔遗传病基因，参与的蛋白质-蛋白质相互作用显著更多，且在进化上更为古老。综上，上述结果表明MENDELSEEK相较现有方法实现了重大突破，同时为区分孟德尔与非孟德尔遗传病基因的生化特征提供了全新的研究视角。